Overview of NTCIR-9 RITE: Recognizing Inference in TExt
Overview of NTCIR-9 RITE: Recognizing Inference in TExt
复制标题
DOI：
--
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
Hideki Shima;H. Kanayama;Cheng-Wei Lee;Chuan-Jie Lin;T. Mitamura;Yusuke Miyao;Shuming Shi;Koichi Takeda-Ko
中科院分区：
文献类型：
--
作者：
Hideki Shima;H. Kanayama;Cheng-Wei Lee;Chuan-Jie Lin;T. Mitamura;Yusuke Miyao;Shuming Shi;Koichi Takeda-Ko
本文介绍了ntcirr -9中RITE （recognition Inference in TExt）任务的概况。我们评估了自动识别日文、简体中文或繁体中文文本之间的蕴涵、释义和矛盾的系统。该任务包括四个子任务：蕴涵二元分类；包括释义和矛盾（MC）在内的多类分类；以及两个外在的面向应用的数据集：入学考试和RITE4QA。本文还描述了我们如何构建测试集合、评估度量，以及提交运行的评估结果。
This paper introduces an overview of the RITE (Recognizing Inference in TExt) task in NTCIR-9. We evaluate systems that automatically recognize entailment, paraphrase, and contradiction between two texts written in Japanese, Simplified Chinese, or Traditional Chinese. The task consists of four subtasks: Binary classification of entailment (BC); Multi-class classification including paraphrase and contradiction (MC); and two extrinsic application-oriented datasets: Entrance Exam and RITE4QA. This paper also describes how we built the test collection, evaluation metrics, and evaluation results of the submitted runs.